Tracing the origin of beer samples by NMR and chemometrics: Trappist beers as a case study

An NMR and chemometric analytical approach to classify beers according to their brand identity was developed within the European TRACE project (FP6‐2003‐FOOD‐2‐A, contract number: 0060942). Rochefort 8 Trappist beers (47 samples), other Trappist beers (76 samples) and non‐Trappist beers (110 samples) were analyzed by ¹H NMR spectroscopy. Selected NMR signals were measured and used to build classification models. Three different classification problems were identified, namely Trappist versus non‐Trappist, Rochefort versus Non‐Rochefort, and Rochefort 8 versus non‐Rochefort 8. In all the three cases, both a discriminant and a modeling approaches were followed, using partial least squares discriminant analysis (PLS‐DA) and soft independent modeling of class analogies (SIMCA), respectively, leading to very high classification accuracy as evaluated by external validation. Information regarding chemical composition was also obtained: Trappist beers contain a higher amount of formic and pyruvic acids and a lower amount of acetic acid and alanine with respect to non‐Trappist ones. Rochefort beers turned out to have also a higher content of propanol and isopentanol with respect to non‐Rochefort samples. Finally, Rochefort 8, shows the highest content of pyruvic acid and the lowest content of gallic, fumaric, acetic acids, adenosine, uridine, 2‐phenylethanol, GABA, and alanine.     

Bridging the gap between metabolic profile determination and visualization in neurometabolic disorders: a multivariate analysis of proton magnetic resonance in vivo spectra

The purpose of this work was to check the degree of overlap between rare inborn errors of metabolism and other neurological disorders using principal component analysis of proton magnetic resonance spectroscopy (¹H MRS) in vivo data. We examined 60 patients (median age of 22 months). Fourteen of them were diagnosed with neurometabolic disorders (three cases of metachromatic leukodystrophy, two cases of Canavan disease, two cases of megalencephalic leukoencephalopathy with subcortical cysts, three cases of mitochondrial cytopathy, one case of nonketotic hyperglycinemia, one case of globoid leukodystrophy, one case of congenital disorders of glycosylation, and one case of ethylmalonic encephalopathy). The remaining 46 patients were diagnosed with epilepsy, cerebral palsy, and developmental delay. Results obtained from principal component analysis of complete unresolved ¹H MRS in vivo spectra were interpreted parallelly with LCModel‐derived metabolite levels. The main attention was paid to the following metabolites: N‐acetylaspartate, glutamate + glutamine, creatine, choline, myo‐inositol signal with an uncertain contribution of glycine, and glucose. ¹H MRS in vivo coupled with multivariate analysis is an efficient tool in visualization of metabolic abnormalities in several inborn errors of metabolism (metachromatic leukodystrophy, globoid leukodystrophy, megalencephalic leukoencephalopathy with subcortical cysts, and Canavan disease). Copyright © 2013 John Wiley & Sons, Ltd.     

Classification of biodiesel using NIR spectrometry and multivariate techniques

This article describes the classification of biodiesel samples using NIR spectroscopy and chemometric techniques. A total of 108 spectra of biodiesel samples were taken (being three samples each of four types of oil, cottonseed, sunflower, soybean and canola), from nine manufacturers. The measurements for each of the three samples were in the spectral region between 12,500 and 4000 cm⁻¹. The data were preprocessed by selecting a spectral range of 5000-4500 cm⁻¹, and then a Savitzky-Golay second-order polynomial was used with 21 data points to obtain second derivative spectra. Characterization of the biodiesel was done using chemometric models based on hierarchical cluster analysis (HCA), principal component analysis (PCA) and soft independent modeling of class analogy (SIMCA) elaborated for each group of biodiesel samples (cotton, sunflower, soybean and canola). For the HCA and PCA, the formation of clusters for each group of biodiesel was observed, and SIMCA models were built using 18 spectral measurements for each type of biodiesel (training set), and nine spectral measurements to construct a classification set (except for the canola oil which used eight spectra). The SIMCA classifications obtained 100% accurate identifications. Using this strategy, it was feasible to classify biodiesel quickly and nondestructively without the need for various analytical determinations.     

Correlation‐assisted nearest shrunken centroid classifier with applications for high dimensional spectral data

High throughput data are frequently observed in contemporary chemical studies. Classification through spectral information is an important issue in chemometrics. Linear discriminant analysis (LDA) fails in the large‐p‐small‐n situation for two main reasons: (1) the sample covariance matrix is singular when p > n and (2) there is an accumulation of noise in the estimation of the class centroid in high dimensional feature space. The Independence Rule is a class of methods used to overcome these drawbacks by ignoring the correlation information between spectral variables. However, a strong correlation is an essential characteristic of spectral data. We proposed a new correlation‐assisted nearest shrunken centroid classifier (CA‐NSC) to incorporate correlation information into the classification. CA‐NSC combines two sources of information [class centroid (mean) and correlation structure (variance)] to generate the classification. We used two real data analyses and a simulation study to verify our CA‐NSC method. In addition to NSC, we also performed a comparison with the soft independent modeling of class analogy (SIMCA) approach, which uses only correlation structure information for classification. The results show that CA‐NSC consistently improves on NSC and SIMCA. The misclassification rate of CA‐NSC is reduced by almost half compared with NSC in one of the real data analyses. Generally, correlation among variables will worsen the performance of NSC, even though the discriminatory information contained in the class centroid remains unchanged. If only correlation structure information is used (as in the case of SIMCA), the result will be satisfactory only when the correlation structure alone can provide sufficient information for classification. Copyright © 2015 John Wiley & Sons, Ltd.     

Towards a complete identification of orthogonal variation in multiple regression from a PLS1 modeling point of view: including OPLS by a change of orthogonal basis

It is well known that the predictions of the single response orthogonal projections to latent structures (OPLS) and the single response partial least squares regression (PLS1) regression are identical in the single‐response case. The present paper presents an approach to identification of the complete y ‐orthogonal structure by starting from the viewpoint of standard PLS1 regression. Three alternative non‐deflating OPLS algorithms and a modified principal component analysis (PCA)‐driven method (including MATLAB code) is presented. The first algorithm implements a postprocessing routine of the standard PLS1 solution where QR factorization applied to a shifted version of the non‐orthogonal scores is the key to express the OPLS solution. The second algorithm finds the OPLS model directly by an iterative procedure. By a rigorous mathematical argument, we explain that orthogonal filtering is a ‘built‐in’ property of the traditional PLS1 regression coefficients. Consequently, the capabilities of OPLS with respect to improving the predictions (also for new samples) compared with PLS1 are non‐existing. The PCA‐driven method is based on the fact that truncating off one dimension from the row subspace of X results in a matrix X _orth with y ‐orthogonal columns and a rank of one less than the rank of X . The desired truncation corresponds exactly to the first X deflation step of Martens non‐orthogonal PLS algorithm. The significant y ‐orthogonal structure of X found by PCA of X _orth is split into two fundamental parts: one part that is significantly contributing to correct the first PLS score toward y and one part that is not. The third and final OPLS algorithm presented is a modification of Martens non‐orthogonal algorithm into an efficient dual PLS1–OPLS algorithm. Copyright © 2014 John Wiley & Sons, Ltd.     

Das dynamische Verhalten des Hydridotris(3,5‐dimethylpyrazolyl)borat‐Liganden in Organopalladium(II)‐Komplexen

The Dynamic Behaviour of Hydridotris(3,5‐dimethylpyrazolyl)borate Ligand in Organopalladium(II) Complexes The new palladium(II) complexes [PdTp*(R)(PPh₃)] (R = Me ( 1 ), C(O)Me ( 1 a ), p‐tol ( 2 ), C(O)p‐tol ( 2 a )) of the tridentate nitrogen ligand Tp* = [HB(3,5‐Me₂pz)₃]^– are non‐rigid molecules on the NMR time scale at room temperature. The ¹H‐NMR spectra at low temperature indicate C_s‐symmetry for 1 whereas 1 a , 2 , 2 a are symmetryless (C₁). The difference in temperature dependence of the ¹H‐NMR spectra is not indicative of a different exchange mechanism. We postulate that in all cases an intramolecular substitution of coordinated and non‐coordinated pyrazolyl substituents takes place. We do not observe a rapid Turnstile rotation of a trigonal bipyramidal intermediate. The crystal structure analysis shows that the coordination of the palladium atom in complex 1 is planar.     

Discrimination and classification techniques applied on Mallotus and Phyllanthus high performance liquid chromatography fingerprints

Mallotus and Phyllanthus genera, both containing several species commonly used as traditional medicines around the world, are the subjects of this discrimination and classification study. The objective of this study was to compare different discrimination and classification techniques to distinguish the two genera (Mallotus and Phyllanthus) on the one hand, and the six species (Mallotus apelta, Mallotus paniculatus, Phyllanthus emblica, Phyllanthus reticulatus, Phyllanthus urinaria L. and Phyllanthus amarus), on the other. Fingerprints of 36 samples from the 6 species were developed using reversed-phase high-performance liquid chromatography with ultraviolet detection (RP-HPLC-UV). After fingerprint data pretreatment, first an exploratory data analysis was performed using Principal Component Analysis (PCA), revealing two outlying samples, which were excluded from the calibration set used to develop the discrimination and classification models. Models were built by means of Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Classification and Regression Trees (CART) and Soft Independent Modeling of Class Analogy (SIMCA). Application of the models on the total data set (outliers included) confirmed a possible labeling issue for the outliers. LDA, QDA and CART, independently of the pretreatment, or SIMCA after “normalization and column centering (N_CC)” or after “Standard Normal Variate transformation and column centering (SNV_CC)” were found best to discriminate the two genera, while LDA after column centering (CC), N_CC or SNV_CC; QDA after SNV_CC; and SIMCA after N_CC or after SNV_CC best distinguished between the 6 species. As classification technique, SIMCA after N_CC or after SNV_CC results in the best overall sensitivity and specificity.     

Chemometrics‐enhanced laser‐induced thermal emission detection of PETN and other explosives on various substrates

Infrared emissions (IREs) of samples of pentaerythritol tetranitrate (PETN) deposited as contamination residues on various substrates were measured to generate models for the detection and discrimination of the important nitrate ester from the emissions of the substrates. Mid‐infrared emissions were generated by heating the samples remotely using laser‐induced thermal emission (LITE). Chemometrics multivariate analysis techniques such as principal component analysis (PCA), soft independent modeling by class analogy (SIMCA), partial least squares‐discriminant analysis (PLS‐DA), support vector machines (SVMs), and neural network (NN) were employed to generate the models for the classification and discrimination of PETN IREs from substrate thermal emissions. PCA exhibited less variability for the LITE spectra of PETN/substrates. SIMCA was able to predict only 44.7% of all samples, while SVM proved to be the most effective statistical analysis routine, with a discrimination performance of 95%. PLS‐DA and NN achieved prediction accuracies of 94% and 88%, respectively. High sensitivity and specificity values were achieved for five of the seven substrates investigated. Copyright © 2015 John Wiley & Sons, Ltd.     

Multivariate analysis for 1H-NMR spectra of two hundred kinds of tea in the world.

NMR measurements coupled with pattern-recognition analysis offer a powerful mixture-analysis tool for latent-feature extraction and sample classification. As fundamental applications of this analysis for mixtures, the 1H spectra of 176 kinds of green, black, oolong and other tea infusions were acquired by a 500 MHz NMR spectrometer. Each spectrum pattern was analyzed by a multivariate statistical pattern-recognition method where Principal Component Analysis (PCA) was used in combination with Soft Independent Modeling of Class Analogy (SIMCA). SIMCA effectively selected variables that contribute to tea categorization. The final PCA resulted in clear classification reflecting the fermentation and processing of each tea, and revealed marker variables that include catechin and theanine peaks.     

N‐Alkylacylamides in Thin Films Display Infrared Spectra of 310‐, α‐, and π‐Helices with Visible Static and Dynamic Growth Phases

A peptide model is a physical system containing a CONH group, the simplest being HCONHCH₃, N‐methylformamide (NMF). We have discovered that NMF and N‐methylacetamide (NMA), which form hydrogen‐bonded oligomers in thin films on a planar AgX fiber, display infrared (IR) spectra with peaks like those of polypeptide helices. Structures can be assigned by their amide I maxima near 1672 (3₁₀), 1655 (3₁₀), 1653 (α), 1655 (π), and 1635 cm^?1 (π), which are the first IR data for the π‐helix. Sharp peaks are an outcome of immobilization of polar species on the polar surface of silver halides. We report the first use of expanded thin‐film IR spectroscopy, in which plots of every spectrum over the amide I–II range show pauses or slow stages in the increase or decrease of absorption. These are identified as static phases followed by dynamic phases, with the incremental gain or loss of a helix turn. A general theory can be stated for such processes. Density functional calculations show that the NMA α‐helix pentamer (crystal structure geometry) is transformed into a π‐helix‐like form. For the first time, an entire sequence (3₁₀‐helix, α‐helix, π‐helix, quasiplanar species) of spectra has been recorded for NMA.     

Cobalt(II) chloro complexation in N-methylformamide–N, N-dimethylformamide mixtures

Cobalt(II) chloro complexation has been studied by titration calorimetry and spectrophotometry in solvent mixtures of N-methylformamide (NMF) and N,N-dimethylformamide (DMF). It revealed that a series of mononuclear CoCln_n ^(2–n)+ (n=1–4) complexes are formed in the mixtures of NMF mole fraction x _NMF=0.05 and 0.25, and the CoCl⁺, CoCl₃ ^– and CoCl₄ ^2– complexes in the mixture of x _NMF=0.5, and their formation constants, enthalpies and entropies were obtained. As compared with DMF, the complexation is markedly suppressed in the mixtures, as well as in NMF. The decreasing formation constant of CoCl⁺ with the NMF content is mainly ascribed to the decreasing formation entropy. DMF is aprotic and thus less-structured, whereas NMF is protic to form hydrogen- bonded clusters. In DMF-NMF mixtures, solvent clusters in neat NMF are ruptured to yield new clusters involving DMF, the structure of which depends on the solvent composition. The entropy of formation of CoCl⁺ will be discussed in relation to the liquid structure of DMF, NMF and their mixtures.     

Effect of Temperature and Solvent on the Structure of Amide Cavitands

Conformational changes of amide cavitands A – C were investigated at varied temperatures and in several solvents. While cavitands A and B , with comparatively smaller substituents such as Et and ⁱPr, were always in vase conformation in non‐polar solvents such as CDCl₃, CD₂Cl₂, (D₈)THF, and C₆D₆, their thermoswitching (vase to kite) was observed in polar solvents such as (D₇)DMF and (D₆)DMSO or in the presence of acid (TFA) and H‐bonding inhibitor (TFE). Intra‐ and interannular H‐bonds of A and B were clearly observed by low‐temperature ¹H‐NMR spectra in CDCl₃. No conformational change of cavitand C with bigger substituent (^tBu) was observed under any tested temperature range and in polar or non‐polar solvents; C was always in the kite conformation.     

Tizanidine and tizanidine hydrochloride: on the correct tautomeric form of tizanidine

A crystallization series of tizanidine hydrochloride, used as a muscle relaxant for spasticity acting centrally as an α₂‐adrenergic agonist, yielded single crystals of the free base and the hydrochloride salt. The crystal structures of tizanidine [systematic name: 5‐chloro‐N‐(imidazolidin‐2‐ylidene)‐2,1,3‐benzothiadiazol‐4‐amine], C₉H₈ClN₅S, (I), and tizanidine hydrochloride {systematic name: 2‐[(5‐chloro‐2,1,3‐benzothiadiazol‐4‐yl)amino]imidazolidinium chloride}, C₉H₉ClN₅S⁺·Cl⁻, (II), have been determined. Tizanidine crystallizes with two almost identical molecules in the asymmetric unit (r.m.s. deviation = 0.179 Å for all non‐H atoms). The molecules are connected by N—H...N hydrogen bonds forming chains running along [21]. The present structure determination corrects the structure determination of tizanidine by John et al. [Acta Cryst. (2011), E 67 , o838–o839], which shows an incorrect tautomeric form. Tizanidine does not crystallize as the usually drawn 2‐amino–imidazoline tautomer, but as the 2‐imino–imidazolidine tautomer. This tautomer is present in solution as well, as shown by ¹H NMR analysis. In tizanidine hydrochloride, cations and anions are connected by N—H...Cl hydrogen bonds to form layers parallel to (100).     

Application to classification of mulberry leaves using multivariate analysis of proton NMR metabolomic data

Recently, NMR-based metabolomic analysis has been used to acquire information based on differentiation among biological samples. In the present study, we examined whether multivariate analysis was able to be applied to natural products and/or material field. Each extraction of 24 leaf samples, divided into six locations from the tip of the stem in each of four strains, was analyzed by pattern recognition methods, known as Principal Component Analysis (PCA) and Soft Independent Modeling of Class Analogy (SIMCA). Twenty-four extracts from mulberry leaf showed independent spectra by 1H NMR. The separation of leaf extraction data due to the difference at six locations was achieved in the PCA score plot as correlation PC1 (86.1%) and PC3 (4.6%) and showed two loading plots, suggesting classification by leaf position as an independent variable in the loading plot. Moreover, the difference among six locations clarified the seven highest discrimination powers by the SIMCA method. Meanwhile, the PCA score plot obtained classification by the variety of mulberry strains with three loading plots, but the SIMCA method did not give a peak by classification.     

Leptocarposide: a new triterpenoid glycoside from Ludwigia leptocarpa (Onagraceae)

A new triterpenoid bidesmoside (leptocarposide) possessing an acyl group in their glycosidic moiety (1), together with the known luteolin‐8‐C‐glucoside (2) and 1‐O‐β‐d ‐glucopyranosyl‐(2S,3R,8E)‐2‐[(2′R)‐2‐hydroxypalmitoylamino]‐8‐octadecen‐1,3‐diol (3) was isolated from the n‐butanol‐soluble fraction of whole plant of Ludwigia leptocarpa (Nutt) Hara (Onagraceae). Structure of compound 1 has been assigned on the basis of spectroscopic data (¹H and ¹³C NMR, ¹H‐¹H COSY, HSQC, HMBC, and ROESY), mass spectrometry, and by comparison with the literature. This compound was further screened for its potential antioxidant properties by using the radical scavenging assay model 2,2‐diphenyl‐1‐picrylhydrazyl and reveals non‐potent antioxidant activities, while compound 2 shows SC₅₀ of 0,038 mM. Copyright © 2013 John Wiley & Sons, Ltd.     

1H‐NMR Analysis of Intra‐ and Intermolecular H‐Bonds of Alcohols in DMSO: Chemical Shift of Hydroxy Groups and Aspects of Conformational Analysis of Selected Monosaccharides,Inositols, and Ginkgolides

The interpretation of ¹H‐NMR chemical shifts, coupling constants, and coefficients of temperature dependence (δ(OH), J(H,OH), and Δδ(OH)/ΔT values) evidences that, in (D₆)DMSO solution, the signal of an OH group involved as donor in an intramolecular H‐bond to a hydroxy or alkoxy group is shifted upfield, whereas the signal of an OH group acting as acceptor of an intramolecular H‐bond and as donor in an intermolecular H‐bond to (D₆)DMSO is shifted downfield. The relative strength of the intramolecular H‐bond depends on co‐operativity and on the acidity of OH groups. The acidity of OH groups is enhanced when they are in an antiparallel orientation to a C−O bond. A comparison of the ¹H‐NMR spectra of alcohols in CDCl₃ and (D₆)DMSO allows discrimination between weak and strong intramolecular H‐bonds. Consideration of IR spectra (CHCl₃ or CH₂Cl₂) shows that the rule according to which the downfield shift of δ(OH) for H‐bonded alcohols in CDCl₃ parallels the strength of the H‐bond is valid only for alcohols forming strong intramolecular H‐bonds. The combined analysis of J(H,OH) and δ(OH) values is illustrated by the interpretation of the spectra of the epoxyalcohols 14 and 15 (Fig. 3). H‐Bonding of hexopyranoses, hexulopyranoses, alkyl hexopyranosides, alkyl 4,6‐O‐benzylidenehexopyranosides, levoglucosans, and inositols in (D₆)DMSO was investigated. Fully solvated non‐anomeric equatorial OH groups lacking a vicinal axial OR group (R=H or alkyl, or (alkoxy)alkyl) show characteristic J(H,OH) values of 4.5 – 5.5 Hz and fully solvated non‐anomeric axial OH groups lacking an axial OR group in β‐position are characterized by J(H,OH) values of 4.2 – 4.4 Hz (Figs. 4 – 6). Non‐anomeric equatorial OH groups vicinal to an axial OR group are involved in a partial intramolecular H‐bond (J(H,OH)=5.4 – 7.4 Hz), whereas non‐anomeric equatorial OH groups vicinal to two axial OR form partial bifurcated H‐bonds (J(H,OH)=5.8 – 9.5 Hz). Non‐anomeric axial OH groups form partial intramolecular H‐bonds to a cis‐1.3‐diaxial alkoxy group (as in 29 and 41 : J(H,OH)=4.8 – 5.0 Hz). The persistence of such a H‐bond is enhanced when there is an additional H‐bond acceptor, such as the ring O‐atom ( 43 – 47 : J(H,OH)=5.6 – 7.6 Hz; 32 and 33 : 10.5 – 11.3 Hz). The (partial) intramolecular H‐bonds lead to an upfield shift (relative to the signal of a fully solvated OH in a similar surrounding) for the signal of the H‐donor. The shift may also be related to the signal of the fully solvated, equatorial HO−C(2), HO−C(3), and HO−C(4) of β‐D ‐glucopyranose ( 16 : 4.81 ppm) by using the following increments: −0.3 ppm for an axial OH group, 0.2 – 0.25 ppm for replacing a vicinal OH by an OR group, ca. 0.1 ppm for replacing another OH by an OR group, 0.2 ppm for an antiperiplanar C−O bond, −0.3 ppm if a vicinal OH group is (partially) H‐bonded to another OR group, and −0.4 to −0.6 for both OH groups of a vicinal diol moiety involved in (partial) divergent H‐bonds. Flip‐flop H‐bonds are observed between the diaxial HO−C(2) and HO−C(4) of the inositol 40 (J(H,OH)=6.4 Hz, δ(OH)=5.45 ppm) and levoglucosan ( 42 ; J(H,OH)=6.7 – 7.1 Hz, δ(OH)=4.76 – 4.83 ppm; bifurcated H‐bond); the former is completely persistent and the latter to ca. 40%. A persistent, unidirectional H‐bond C(1)−OH⋅⋅⋅O−C(10) is present in ginkgolide B and C, as evidenced by strongly different δ(OH) and Δδ(OH)/ΔT values for HO−C(1) and HO−C(10) (Fig. 9). In the absence of this H‐bond, HO−C(1) of 52 resonates 1.1 – 1.2 ppm downfield, while HO−C(10) of ginkgolide A and of 48 – 50 resonates 0.5 – 0.9 ppm upfield.     

Overlapping spectra resolution using non-negative matrix factorization

Non-negative matrix factorization (NMF), with the constraints of non-negativity, has been recently proposed for multi-variate data analysis. Because it allows only additive, not subtractive, combinations of the original data, NMF is capable of producing region or parts-based representation of objects. It has been used for image analysis and text processing. Unlike PCA, the resolutions of NMF are non-negative and can be easily interpreted and understood directly. Due to multiple solutions, the original algorithm of NMF [D.D. Lee, H.S. Seung, Nature 401 (1999) 788] is not suitable for resolving chemical mixed signals. In reality, NMF has never been applied to resolving chemical mixed signals. It must be modified according to the characteristics of the chemical signals, such as smoothness of spectra, unimodality of chromatograms, sparseness of mass spectra, etc. We have used the modified NMF algorithm to narrow the feasible solution region for resolving chemical signals, and found that it could produce reasonable and acceptable results for certain experimental errors, especially for overlapping chromatograms and sparse mass spectra. Simulated two-dimensional (2-D) data and real GUJINGGONG alcohol liquor GC-MS data have been resolved soundly by NMF technique. Butyl caproate and its isomeric compound (butyric acid, hexyl ester) have been identified from the overlapping spectra. The result of NMF is preferable to that of Heuristic evolving latent projections (HELP). It shows that NMF is a promising chemometric resolution method for complex samples.     

Comparison of chemometric methods for brand classification of cigarettes by near-infrared spectroscopy

The combinations of NIR spectroscopy and three classification algorithms, i.e., multi-class support vector machine (BSVM), k-nearest neighbor (KNN) and soft independent modeling of class analogies (SIMCA), for discriminating different brands of cigarettes, were explored. The influence of the training set size on the relative performance of each algorithm was also investigated. A NIR spectral dataset involving the classification of cigarettes of three brands was used for illustration. Three performance criteria based on “correctly classified rate (CCR)”, i.e., “Average CCR”, “95 percentile of CCR” and “S.D. of CCR”, were defined to compare different algorithms. It was revealed that BSVM is significantly better than KNN or SIMCA in the statistical sense, especially in cases where the training set is relatively small. The results suggest that NIR spectroscopy together with BSVM could be an alternative to traditional methods for discriminating different brands of cigarettes.